COVID-19 Analysis
Katie Forthman
Fri May 29 11:23:30 2020
Click here for interactive plots:
Click here to see how cities and counties overlap:
Compare COVID stats to Neighborhood Factors
data.cor <- cor(county.Demo_and_Covid.allcounties[,-1], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
Compare COVID stats to 500 cities data and Neighborhood Factors
data.cor2 <- cor(county.Demo_and_Covid.500counties[,-c(1:2)], use = "complete.obs", method = "spearman")
corrplot.mixed(data.cor2, upper = 'ellipse', lower = 'number', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
corrplot.mixed(data.cor2[7:13,c(1:5, 14:42,6)], upper = 'ellipse', tl.pos = 'lt', tl.cex = 1, lower.col = "black", number.cex = 0.5)
—-Linear Mixed Effects Model —-
this.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)", data = county.Demo_and_Covid.500counties)## Warning: Some predictor variables are on very different scales: consider
## rescaling
## Warning: Some predictor variables are on very different scales: consider
## rescalingprint(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + Testing_Rate + Hospitalization_Rate + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -1272.7
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.3277 -0.3735 -0.0440 0.2666 5.7822
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.000006139 0.002478
## Residual 0.000015544 0.003943
## Number of obs: 192, groups: stateID, 35
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0106730365 0.0117383172 99.6522998052
## Affluence 0.0047825383 0.0011856547 145.0763321353
## Singletons.in.Tract 0.0009251830 0.0010045295 171.9763799445
## Seniors.in.Tract 0.0005189321 0.0013089203 171.6914089336
## African.Americans.in.Tract 0.0012167680 0.0011112903 171.9326569088
## Noncitizens.in.Tract 0.0017253193 0.0008579755 153.5283884113
## High.BP 0.0000070266 0.0002120131 156.2000441759
## Binge.Drinking 0.0003594433 0.0002028032 73.6065252569
## Cancer -0.0020357477 0.0012679767 146.9532550504
## Asthma 0.0001104857 0.0006835234 78.0008002594
## Heart.Disease 0.0028905515 0.0015902856 123.4821298686
## COPD -0.0001498570 0.0013112344 122.6011126894
## Smoking -0.0002067749 0.0002638750 138.5395917435
## Diabetes -0.0007862429 0.0006445205 125.9220623076
## No.Physical.Activity 0.0000313720 0.0002443292 137.0879757406
## Obesity 0.0003719539 0.0002024264 162.9759143724
## Poor.Sleeping.Habits 0.0000861246 0.0001835164 159.5936574679
## Poor.Mental.Health -0.0000602589 0.0005550160 50.9501886022
## Testing_Rate 0.0000007601 0.0000002927 46.3396086292
## Hospitalization_Rate -0.0001329402 0.0001234193 32.9280596003
## t value Pr(>|t|)
## (Intercept) -0.909 0.3654
## Affluence 4.034 0.0000885 ***
## Singletons.in.Tract 0.921 0.3583
## Seniors.in.Tract 0.396 0.6923
## African.Americans.in.Tract 1.095 0.2751
## Noncitizens.in.Tract 2.011 0.0461 *
## High.BP 0.033 0.9736
## Binge.Drinking 1.772 0.0805 .
## Cancer -1.606 0.1105
## Asthma 0.162 0.8720
## Heart.Disease 1.818 0.0715 .
## COPD -0.114 0.9092
## Smoking -0.784 0.4346
## Diabetes -1.220 0.2248
## No.Physical.Activity 0.128 0.8980
## Obesity 1.837 0.0680 .
## Poor.Sleeping.Habits 0.469 0.6395
## Poor.Mental.Health -0.109 0.9140
## Testing_Rate 2.597 0.0126 *
## Hospitalization_Rate -1.077 0.2892
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence 0.010
## Sngltns.n.T 0.023 0.068
## Snrs.n.Trct 0.474 0.345 0.190
## Afrcn.Am..T 0.122 0.146 -0.388 0.147
## Nnctzns.n.T 0.006 0.122 0.038 0.094 -0.126
## High.BP -0.079 0.261 0.018 0.073 -0.067 0.342
## Bing.Drnkng -0.391 -0.121 -0.277 -0.116 0.063 -0.015 0.130
## Cancer -0.552 -0.103 0.211 -0.250 -0.077 -0.083 -0.334 -0.052
## Asthma -0.413 -0.096 -0.266 -0.211 0.077 0.095 0.117 0.040 0.041
## Heart.Dises -0.188 0.063 -0.310 -0.177 0.251 -0.137 0.058 0.067 -0.486
## COPD 0.578 0.004 0.162 0.267 -0.045 0.246 0.067 0.026 -0.255
## Smoking -0.100 0.112 -0.178 -0.125 -0.045 0.063 -0.035 -0.280 0.082
## Diabetes 0.155 -0.384 -0.089 -0.192 -0.302 -0.233 -0.553 0.038 0.235
## N.Physcl.Ac -0.215 0.073 0.108 0.015 -0.018 -0.218 -0.007 0.120 0.442
## Obesity -0.024 0.379 0.478 0.283 0.104 0.162 -0.100 -0.188 0.118
## Pr.Slpng.Hb -0.407 -0.391 0.112 -0.324 -0.278 -0.071 -0.184 0.110 0.094
## Pr.Mntl.Hlt -0.364 0.226 -0.053 -0.025 0.070 -0.118 0.026 0.122 0.349
## Testing_Rat 0.222 -0.148 0.025 0.007 0.011 -0.028 -0.043 -0.083 -0.170
## Hsptlztn_Rt -0.137 -0.127 -0.056 -0.180 -0.040 -0.114 -0.036 -0.076 -0.060
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H Pr.M.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.328
## COPD -0.409 -0.584
## Smoking 0.106 0.176 -0.465
## Diabetes -0.144 -0.360 0.012 0.212
## N.Physcl.Ac 0.069 -0.342 -0.017 -0.289 -0.167
## Obesity -0.210 -0.089 0.149 -0.253 -0.368 -0.003
## Pr.Slpng.Hb 0.089 0.257 -0.159 -0.079 -0.035 -0.155 -0.138
## Pr.Mntl.Hlt -0.253 0.076 -0.451 0.021 -0.011 0.005 0.023 -0.126
## Testing_Rat -0.297 -0.086 0.237 0.104 0.148 -0.299 0.081 -0.125 -0.150
## Hsptlztn_Rt 0.050 0.164 -0.131 0.083 -0.023 0.004 0.006 0.007 -0.089
## Tstn_R
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises
## COPD
## Smoking
## Diabetes
## N.Physcl.Ac
## Obesity
## Pr.Slpng.Hb
## Pr.Mntl.Hlt
## Testing_Rat
## Hsptlztn_Rt 0.096
## fit warnings:
## Some predictor variables are on very different scales: consider rescalingthis.lme <- lmer("total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)", data = county.Demo_and_Covid.500counties)
print(summary(this.lme), correlation=TRUE)## Linear mixed model fit by REML. t-tests use Satterthwaite's method [
## lmerModLmerTest]
## Formula:
## "total.cases.percap ~ Affluence + Singletons.in.Tract + Seniors.in.Tract + African.Americans.in.Tract + Noncitizens.in.Tract + High.BP + Binge.Drinking + Cancer + Asthma + Heart.Disease + COPD + Smoking + Diabetes + No.Physical.Activity + Obesity + Poor.Sleeping.Habits + Poor.Mental.Health + (1 | stateID)"
## Data: county.Demo_and_Covid.500counties
##
## REML criterion at convergence: -2415.1
##
## Scaled residuals:
## Min 1Q Median 3Q Max
## -3.7752 -0.3992 -0.0629 0.2699 6.3971
##
## Random effects:
## Groups Name Variance Std.Dev.
## stateID (Intercept) 0.00000800 0.002828
## Residual 0.00001385 0.003721
## Number of obs: 326, groups: stateID, 51
##
## Fixed effects:
## Estimate Std. Error df
## (Intercept) -0.0236274032 0.0083089268 191.1636565760
## Affluence 0.0032301089 0.0007568732 301.5429902594
## Singletons.in.Tract 0.0007626386 0.0007077702 301.6365993115
## Seniors.in.Tract 0.0009539135 0.0008937561 304.8211395708
## African.Americans.in.Tract 0.0020038355 0.0008637145 307.0311724146
## Noncitizens.in.Tract 0.0020407596 0.0006952358 269.8229467916
## High.BP -0.0000003537 0.0001561438 297.5998350371
## Binge.Drinking 0.0004645230 0.0001634060 156.6532558065
## Cancer -0.0006306463 0.0009148215 264.4285446262
## Asthma 0.0006899500 0.0005413014 139.7260040998
## Heart.Disease 0.0034402502 0.0011719270 207.6078231000
## COPD -0.0014343905 0.0008870296 202.4492995936
## Smoking -0.0001334325 0.0002052925 247.7809563104
## Diabetes -0.0012931217 0.0004401860 266.9339650220
## No.Physical.Activity 0.0003053725 0.0001766569 234.9263053984
## Obesity 0.0002837017 0.0001434690 307.9993641496
## Poor.Sleeping.Habits 0.0002474314 0.0001379948 296.5269083016
## Poor.Mental.Health -0.0001692431 0.0004584917 102.4957980668
## t value Pr(>|t|)
## (Intercept) -2.844 0.00495 **
## Affluence 4.268 0.0000265 ***
## Singletons.in.Tract 1.078 0.28211
## Seniors.in.Tract 1.067 0.28668
## African.Americans.in.Tract 2.320 0.02100 *
## Noncitizens.in.Tract 2.935 0.00362 **
## High.BP -0.002 0.99819
## Binge.Drinking 2.843 0.00507 **
## Cancer -0.689 0.49120
## Asthma 1.275 0.20456
## Heart.Disease 2.936 0.00370 **
## COPD -1.617 0.10742
## Smoking -0.650 0.51632
## Diabetes -2.938 0.00360 **
## No.Physical.Activity 1.729 0.08519 .
## Obesity 1.977 0.04888 *
## Poor.Sleeping.Habits 1.793 0.07398 .
## Poor.Mental.Health -0.369 0.71279
## ---
## Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1##
## Correlation of fixed effects could have been required in summary()##
## Correlation of Fixed Effects:
## (Intr) Afflnc Sng..T Snr..T A.A..T Nnc..T Hgh.BP Bng.Dr Cancer
## Affluence -0.047
## Sngltns.n.T -0.057 0.044
## Snrs.n.Trct 0.398 0.293 0.074
## Afrcn.Am..T 0.242 0.076 -0.405 0.201
## Nnctzns.n.T -0.072 0.153 0.126 0.057 -0.189
## High.BP -0.096 0.157 0.099 0.007 -0.235 0.330
## Bing.Drnkng -0.486 -0.043 -0.206 -0.070 0.042 -0.076 0.149
## Cancer -0.496 -0.096 0.231 -0.174 -0.073 -0.068 -0.329 -0.021
## Asthma -0.267 -0.098 -0.262 -0.120 -0.011 0.210 0.055 0.006 -0.158
## Heart.Dises -0.057 0.075 -0.300 -0.132 0.212 -0.053 -0.003 0.034 -0.602
## COPD 0.479 0.012 0.127 0.173 -0.004 0.156 0.060 0.061 -0.214
## Smoking -0.046 0.105 -0.119 -0.137 -0.105 0.160 -0.083 -0.327 0.159
## Diabetes 0.036 -0.300 -0.079 -0.133 -0.230 -0.256 -0.444 0.075 0.365
## N.Physcl.Ac -0.115 0.033 0.101 0.079 0.060 -0.274 0.004 0.124 0.338
## Obesity -0.065 0.384 0.398 0.203 0.134 0.195 -0.104 -0.149 0.119
## Pr.Slpng.Hb -0.386 -0.352 0.163 -0.327 -0.322 -0.046 -0.156 0.087 0.029
## Pr.Mntl.Hlt -0.354 0.183 -0.007 0.019 0.050 -0.166 0.026 0.131 0.417
## Asthma Hrt.Ds COPD Smokng Diabts N.Ph.A Obesty Pr.S.H
## Affluence
## Sngltns.n.T
## Snrs.n.Trct
## Afrcn.Am..T
## Nnctzns.n.T
## High.BP
## Bing.Drnkng
## Cancer
## Asthma
## Heart.Dises 0.336
## COPD -0.324 -0.489
## Smoking 0.144 0.082 -0.476
## Diabetes -0.106 -0.430 -0.011 0.279
## N.Physcl.Ac -0.024 -0.361 0.087 -0.274 -0.169
## Obesity -0.128 -0.021 0.092 -0.220 -0.377 -0.045
## Pr.Slpng.Hb 0.000 0.240 -0.094 -0.165 -0.060 -0.154 -0.115
## Pr.Mntl.Hlt -0.436 -0.067 -0.388 -0.027 0.073 -0.083 0.027 -0.083Testing Rate
testing.data.state <- compiled.stats[[length(daily_filenames)]][, c("Province_State", "Testing_Rate")]
testing.data.state <- testing.data.state[!is.na(testing.data.state$Testing_Rate),]
testing.data.state <- testing.data.state[order(testing.data.state$Testing_Rate),]
col.state <- rep("pink", nrow(testing.data.state))
avg.test.rate <- mean(testing.data.state$Testing_Rate, na.rm = T)
col.state[testing.data.state$Testing_Rate < avg.test.rate] <- "grey"
col.state[testing.data.state$Province_State == "Oklahoma"] <- "lightblue"
par(mar = c(5,6,4,2))
barplot(testing.data.state$Testing_Rate, names.arg = testing.data.state$Province_State, horiz = T, main = "Testing Rate by State", las = 2, cex.axis = 1, cex.names = 0.5, col = col.state, border = F, xlab = "Total number of people tested per 100,000 persons.")
abline(v = avg.test.rate, col = "red")
text(x = avg.test.rate + 10, y = 1, labels = "Average Testing Rate", adj = c(0, 0.5), col = "red")
Pink highlights the last 14 days.
day.first.case <- min(which(US.total$cases.total > 100))
n.days <- nrow(US.total)
twoweek.col <- c(rep("grey", n.days-day.first.case-13), rep("pink", 14))
par(mar = c(5,5,4,2))
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 cases by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Total COVID-19 deaths by Date in US, log scale",
las = 2, cex.axis = 1, cex.names = 0.5, log = "y",
col = twoweek.col, border = F)
barplot(US.total$rise.cases.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Cases of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)
barplot(US.total$rise.deaths.total[day.first.case:n.days],
names = US.total$day[day.first.case:n.days],
main = "Rise in Deaths of COVID-19 by Date in US",
las = 2, cex.axis = 1, cex.names = 0.5,
col = twoweek.col, border = F)